An Information - Theoretic Model of Discourse for Next Utterance Type Prediction

• Item type: Journal(1)
• 公開日: 1994-06-15
• タイトル: An Information - Theoretic Model of Discourse for Next Utterance Type Prediction
• タイトル / 言語: en
• タイトル: An Information - Theoretic Model of Discourse for Next Utterance Type Prediction
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 論文（IPSJ Best Paper Award、論文賞受賞）
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• その他タイトル / その他のタイトル: 音声認識
• 著者所属: ATR Interpreting Telephony Research Laboratories/Presently with NTT Network Information Systems Laboratories
• 著者所属: ATR Interpreting Telephony Research Laboratories/Presently with ATR Interpreting Telecommunications Research Laboratories
• 著者所属(英): en
• 著者所属(英): ATR Interpreting Telephony Research Laboratories/Presently with NTT Network Information Systems Laboratories
• 著者所属(英): en
• 著者所属(英): ATR Interpreting Telephony Research Laboratories/Presently with ATR Interpreting Telecommunications Research Laboratories
• 著者名: Masaaki, Nagata; Tsuyoshi, Morimoto
• 著者名(英): Masaaki, Nagata; Tsuyoshi, Morimoto
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We propose a statistical model of dialogue that is based on an information-theoretic interpretation of discourse to predict the illocutionary force type of the next utterance. The model consists of a second-order Mar.kov model of utterances classified by their illocutionary force types such as REQUEST INFORM etc. and it gives us a criterion for measuring whether the speech recognition candidate forms a natural local discourse in terms of the speech act sequence. By predicting the next utterance in an abstract level we can rule out erroneous speech recognition candidates that are syntactically and semantically correct but contextually incorrect. We show the effectiveness of the statistical dialogue model for utterance type prediction by extensive experiments using 100 telephone dialogues containing 7 531 utterances. The model achieves 61.7 ~6 accuracy for the top candidate and 85.1 % for the top three candidates when 50 dialogues were used for training and the other 50 dialogues were used for testing. We also show that the model can capture the basic characteristics of the local discourse structure such as turn-taking and speech act sequencing and dialogue-type dependent features such as initiative which is the allocation of the control and the manner by which the control is transferred.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We propose a statistical model of dialogue that is based on an information-theoretic interpretation of discourse, to predict the illocutionary force type of the next utterance. The model consists of a second-order Mar.kov model of utterances classified by their illocutionary force types, such as REQUEST, INFORM, etc., and it gives us a criterion for measuring whether the speech recognition candidate forms a natural local discourse in terms of the speech act sequence. By predicting the next utterance in an abstract level, we can rule out erroneous speech recognition candidates that are syntactically and semantically correct, but contextually incorrect. We show the effectiveness of the statistical dialogue model for utterance type prediction by extensive experiments using 100 telephone dialogues containing 7,531 utterances. The model achieves 61.7 ~6 accuracy for the top candidate and 85.1 % for the top three candidates, when 50 dialogues were used for training and the other 50 dialogues were used for testing. We also show that the model can capture the basic characteristics of the local discourse structure, such as turn-taking and speech act sequencing, and dialogue-type dependent features, such as initiative, which is the allocation of the control and the manner by which the control is transferred.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 35, 号 6, p. 1050-1061, 発行日 1994-06-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764